Abstract
We investigated the ability of a Deep Belief Network with logistic nodes, trained unsupervised by Contrastive Divergence, to discover features of evolved abstract art images. Two Restricted Boltzmann Machine models were trained independently on low and high aesthetic class images. The receptive fields (filters) of both models were compared by visual inspection. Roughly 10 % of these filters in the high aesthetic model approximated the form of the high aesthetic training images. The remaining 90 % of filters in the high aesthetic model and all filters in the low aesthetic model appeared noise like. The form of discovered filters was not consistent with the Gabor filter like forms discovered for MNIST training data, possibly revealing an interesting property of the evolved abstract training images. We joined the datasets and trained a Restricted Boltzmann Machine finding that roughly 30 % of the filters approximate the form of the high aesthetic input images. We trained a 10 layer Deep Belief Network on the joint dataset and used the output activities at each layer as training data for traditional classifiers (decision tree and random forest). The highest classification accuracy from learned features (84 %) was achieved at the second hidden layer, indicating that the features discovered by our Deep Learning approach have discriminative power. Above the second hidden layer, classification accuracy decreases.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
We arbitrarily decided 10 layers are sufficient to satisfactorily show any trend in classification accuracy with depth.
- 2.
WEKA J48 and RandomForest classifiers were run with all default settings and 10 fold cross validation.
References
Birkhoff, G.D.: Aesthetic Measure. Mass, Cambridge (1933)
Campbell, A., Ciesielski, V., Trist, K.: A self organizing map based method for understanding features associated with high aesthetic value evolved abstract images. In: 2014 IEEE Congress on Evolutionary Computation (CEC), pp. 2274–2281. IEEE (2014)
Ciesielski, V., Barile, P., Trist, K.: Finding image features associated with high Aesthetic value by machine learning. In: Machado, P., McDermott, J., Carballal, A. (eds.) EvoMUSART 2013. LNCS, vol. 7834, pp. 47–58. Springer, Heidelberg (2013)
Datta, R.: Semantics and aesthetics inference for image search: statistical learning approaches. Pennsylvania State University (2009)
Datta, R., Joshi, D., Li, J., Wang, J.Z.: Studying Aesthetics in photographic images using a computational approach. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 288–301. Springer, Heidelberg (2006)
Erhan, D., Bengio, Y., Courville, A., Vincent, P.: Visualizing higher-layer features of a deep network. Dept. IRO, Université de Montréal, Technical report (2009)
Fischer, A., Igel, C.: Training restricted boltzmann machines: An introduction. Pattern Recogn. 47(1), 25–39 (2014)
Galanter, P.: Computational aesthetic evaluation: past and future. In: McCormack, J., d’Inverno, M. (eds.) Computers and Creativity, pp. 255–293. Springer, Heidelberg (2012)
Ginosar, S., Haas, D., Brown, T., Malik, J.: Detecting people in cubist art. arXiv preprint arXiv:1409.6235 (2014)
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. ACM SIGKDD Explor. Newslett. 11(1), 10–18 (2009)
Hinton, G.: A practical guide to training restricted Boltzmann machines. Momentum 9(1), 926 (2010)
Hinton, G., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Geoffrey, E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771–1800 (2002)
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)
Hoenig, F.: Defining computational aesthetics. In: Neumann, L., Sbert, M., Gooch, B., Purgathofer, W. (eds.) Computational Aesthetics, pp. 13–18. Eurographics Association, London (2005)
Ke, Y., Tang, X., Jing, F.: The design of high-level features for photo quality assessment. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 419–426. IEEE (2006)
LeCun, Y., Cortes, C.: The mnist database of handwritten digits (1998)
Lee, H., Ekanadham, C., Ng, A.Y.: Sparse deep belief net model for visual area v2. In: Platt, J.C., Koller, D., Singer, Y., Roweis, S. (eds.) Advances in Neural Information Processing Systems, pp. 873–880. MIT Press, Cambridge (2008)
Lu, X., Lin, Z., Jin, H., Yang, J., Wang, J.Z.: Rapid: Rating pictorial aesthetics using deep learning. In: Proceedings of the ACM International Conference on Multimedia, pp. 457–466. ACM (2014)
Machado, P., Cardoso, A.: Generation and evaluation of artworks. In: Proceedings of the 1st European Workshop on Cognitive Modeling, CM’96, pp. 96–39 (2010)
Murray, N., Marchesotti, L., Perronnin, F.: Ava: A large-scale database for aesthetic visual analysis. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2408–2415. IEEE (2012)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 807–814 (2010)
Reaves, D.: Aesthetic image rating (AIR) algorithm. Ph.D. thesis (2008)
Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: 2013 12th International Conference on Document Analysis and Recognition, vol. 2, pp. 958–958. IEEE Computer Society (2003)
Spratt, E.L., Elgammal, A.: Computational beauty: Aesthetic judgment at the intersection of art and science. arXiv preprint arXiv:1410.2488 (2014)
Jost Tobias Springenberg and Martin Riedmiller. Improving deep neural networks with probabilistic maxout units. arXiv preprint arXiv:1312.6116 (2013)
Xu, Q., D’Souza, D., Ciesielski, V.: Evolving images for entertainment. In: Proceedings of the 4th Australasian Conference on Interactive Entertainment, p. 26. RMIT University (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Campbell, A., Ciesielksi, V., Qin, A.K. (2015). Feature Discovery by Deep Learning for Aesthetic Analysis of Evolved Abstract Images. In: Johnson, C., Carballal, A., Correia, J. (eds) Evolutionary and Biologically Inspired Music, Sound, Art and Design. EvoMUSART 2015. Lecture Notes in Computer Science(), vol 9027. Springer, Cham. https://doi.org/10.1007/978-3-319-16498-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-16498-4_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16497-7
Online ISBN: 978-3-319-16498-4
eBook Packages: Computer ScienceComputer Science (R0)